Classifications

• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
  • H04N19/103—Selection of coding mode or of prediction mode
  • H04N19/105—Selection of the reference unit for prediction within a chosen coding or prediction mode, e.g. adaptive choice of position and number of pixels used for prediction
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
  • H04N19/103—Selection of coding mode or of prediction mode
  • H04N19/11—Selection of coding mode or of prediction mode among a plurality of spatial predictive coding modes
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/102—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or selection affected or controlled by the adaptive coding
  • H04N19/132—Sampling, masking or truncation of coding units, e.g. adaptive resampling, frame skipping, frame interpolation or high-frequency transform coefficient masking
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
  • H04N19/157—Assigned coding mode, i.e. the coding mode being predefined or preselected to be further used for selection of another element or parameter
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
  • H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
  • H04N19/176—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a block, e.g. a macroblock
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/189—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the adaptation method, adaptation tool or adaptation type used for the adaptive coding
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/46—Embedding additional information in the video signal during the compression process
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
  • H04N19/59—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial sub-sampling or interpolation, e.g. alteration of picture size or resolution
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/50—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding
  • H04N19/593—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using predictive coding involving spatial prediction techniques
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
  • H04N19/61—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding in combination with predictive coding
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
  • H04N19/146—Data rate or code amount at the encoder output
  • H04N19/147—Data rate or code amount at the encoder output according to rate distortion criteria
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
  • H04N19/189—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the adaptation method, adaptation tool or adaptation type used for the adaptive coding
  • H04N19/19—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the adaptation method, adaptation tool or adaptation type used for the adaptive coding using optimisation based on Lagrange multipliers
• • H—ELECTRICITY
  • H04—ELECTRIC COMMUNICATION TECHNIQUE
  • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
  • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
  • H04N19/60—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding
  • H04N19/61—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding in combination with predictive coding
  • H04N19/619—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using transform coding in combination with predictive coding the transform being operated outside the prediction loop

Definitions

• the present application is concerned with an improved intra-prediction mode concept for block-wise picture coding such as usable in a video codec such as HEVC or any successor of HEVC.
• Intra-prediction modes are widely used in picture and video coding.
• intra-prediction modes compete with other prediction modes such as inter-prediction modes such as motion-compensated prediction modes.
• intra-prediction modes a current block is predicted on the basis of neighboring samples, i.e. samples already encoded as far as the encoder side is concerned, and already decoded as far as the decoder side is concerned. Neighboring sample values are extrapolated into the current block so as to form a prediction signal for the current block with the prediction residual being transmitted in the datastream for the current block. The better the prediction signal is, the lower the prediction residual is and, accordingly, a lower number of bits is necessary to code the prediction residual.
• the set of supported intra-prediction modes should be able to provide a good prediction signal, i.e. a prediction signal resulting in a low prediction residual.
• the present application seeks to provide an intra-prediction mode concept allowing for a more efficient compression of a block-wise picture codec if using the improved intra-prediction mode concept.
• an apparatus for block-wise decoding a picture from a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network, wherein the apparatus is configured, for a current block differing from the predetermined size, to:
• an apparatus for block-wise encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network, wherein the apparatus is configured, for a current block differing from the predetermined size, to:
• the apparatus may be configured to resample by downsampling the second template to obtain the first template.
• the apparatus may be configured to resample the preliminary intra-prediction signal by upsampling the preliminary intra-prediction signal.
• the apparatus may be configured to transform the preliminary intra-prediction signal from a spatial domain into a transform domain; and resample the preliminary intra-prediction signal in the transform domain.
• the apparatus may be configured to resample the transform-domain preliminary intra-prediction signal by scaling the coefficients of the preliminary intra-prediction signal.
• the apparatus may be configured to resample the transform-domain preliminary intra-prediction signal by:
• the apparatus may be configured to compose the transform-domain preliminary intra-prediction signal with a dequantized version of a prediction residual signal.
• the apparatus may be configured to resample the preliminary intra-prediction signal in the spatial domain.
• the apparatus may be configured to resample the preliminary intra-prediction signal by performing a bilinear interpolation.
• the apparatus may be configured to encode in a data field information regarding the resampling and/or the use of neural networks for different dimensions.
• an apparatus for block-wise decoding a picture from a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a current block of the picture is determined by: applying a first set of neighboring samples of the current block onto a neural network to obtain a prediction of a set of transform coefficients of a transform of the current block.
• an apparatus for block-wise encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a current block of the picture is determined by: applying a first set of neighboring samples of the current block onto a neural network to obtain a prediction of a set of transform coefficients of a transform of the current block.
• One of the apparatus may be configured to inversely transform the prediction to obtain a reconstructed signal.
• One of the apparatus may be configured to decode from the data stream an index using a variable length code; and perform the selection using the index .
• One of the apparatus may be configured to determine a ranking of the set of intra prediction modes; and, subsequently, resample the second template.
• a method for block-wise decoding a picture from a data stream comprising: applying a first set of neighboring samples of a current block onto a neural network to obtain a prediction of a set of transform coefficients of a transform of a current block.
• a method for block-wise encoding a picture into a data stream comprising: applying a first set of neighboring samples of a current block onto a neural network to obtain a prediction of a set of transform coefficients of a transform of a current block.
• a method of above and/or below may use the equipment comprising at least one apparatus as above and/or below.
• a computer-readable storage medium comprising instructions which, when executed by a computer, cause the computer to perform a method as above and/or below and/or implementing at least one component of the apparatus above and/or below.
• the present application provides many examples for appropriately determining parameters thereof.
• Some examples achieve the compression efficiency increase by spending a set of intra-prediction modes which are neural network-based. The latter ones may be added to other intra-prediction modes heuristically designed, for instance, or may be provided exclusively. Other examples use a neural network in order to perform a selection among a plurality of intra-prediction modes. And even other examples make use of both of the just-discussed specialties.
• Fig. 1 shows an apparatus for block-wise encoding a picture 10 into a datastream 12.
• the apparatus is indicated using reference sign 14 and may be a still picture encoder or a video encoder.
• picture 10 may be a current picture out of a video 16 when the encoder 14 is configured to encode video 16 including picture 10 into datastream 12, or encoder 14 may encode picture 10 into datastream 12 exclusively.
• encoder 14 performs the encoding in a block-wise manner or block-base. To this, encoder 14 subdivides picture 10 into blocks, units of which encoder 14 encodes picture 10 into datastream 12. Examples of possible subdivisions of picture 10 into blocks 18 are set out in more detail below. Generally, the subdivision may end-up into blocks 18 of constant size such as an array of blocks arranged in rows and columns or into blocks 18 of different block sizes such as by use of a hierarchical multi-tree subdivisioning with starting the multi-tree subdivisioning from the whole picture area of picture 10 or from a pre-partitioning of picture 10 into an array of tree blocks wherein these examples shall not be treated as excluding other possible ways of subdivisioning picture 10 into blocks 18.
• encoder 14 is a predictive encoder configured to predictively encode picture 10 into datastream 12. For a certain block 18 this means that encoder 14 determines a prediction signal for block 18 and encodes the prediction residual, i.e. the prediction error at which the prediction signal deviates from the actual picture content within block 18, into datastream 12.
• Encoder 14 may support different prediction modes so as to derive the prediction signal for a certain block 18.
• the prediction modes which are of importance in the following examples, are intra-prediction modes according to which the inner of block 18 is predicted spatially from neighboring, already encoded samples of picture 10.
• the encoding of picture 10 into datastream 12 and, accordingly, the corresponding decoding procedure may be based on a certain coding order 20 defined among blocks 18.
• the coding order 20 may traverse blocks 18 in a raster scan order such as row-wise from top to bottom with traversing each row from left to right, for instance.
• raster scan ordering may be applied within each hierarchy level, wherein a depth-first traversal order may be applied, i.e. leaf notes within a block of a certain hierarchy level may precede blocks of the same hierarchy level having the same parent block according to coding order 20.
• neighboring, already encoded samples of a block 18 may be located usually at one or more sides of block 18. In case of the examples presented herein, for instance, neighboring, already encoded samples of a block 18 are located to the top of, and to the left of block 18.
• Intra-prediction modes may not be the only ones supported by encoder 14.
• encoder 14 may also support intra-prediction modes according to which a block 18 is temporarily predicted from a previously encoded picture of video 16.
• Such an intra-prediction mode may be a motion-compensated prediction mode according to which a motion vector is signaled for such a block 18 indicating a relative spatial offset of the portion from which the prediction signal of block 18 is to be derived as a copy.
• non-intra-prediction modes may be available as well such as inter-view prediction modes in case of encoder 14 being a multi-view encoder, or non-predictive modes according to which the inner of block 18 is coded as is, i.e. without any prediction.
• Fig. 2 shows a possible implementation of encoder 14 of Fig. 1 , namely one where the encoder is configured to use transform coding for encoding the prediction residual although this is nearly an example and the present application is not restricted to that sort of prediction residual coding.
• encoder 14 comprises a subtractor 22 configured to subtract from the inbound signal, i.e. picture 10 or, on a block basis, current block 18, the corresponding prediction signal 24 so as to obtain the prediction residual signal 26 which is then encoded by a prediction residual encoder 28 into a datastream 12.
• the prediction residual encoder 28 is composed of a lossy encoding stage 28a and a lossless encoding stage 28b.
• the lossy stage 28a receives the prediction residual signal 26 and comprises a quantizer 30 which quantizes the samples of the prediction residual signal 26.
• the lossy encoding stage 28a comprises a transform stage 32 connected between subtractor 22 and quantizer 30 so as to transform such a spectrally decomposed prediction residual 26 with a quantization of quantizer 30 taking place on the transformed coefficients where presenting the residual signal 26.
• the transform may be a DCT, DST, FFT, Hadamard transform or the like.
• the transformed and quantized prediction residual signal 34 is then subject to lossless coding by the lossless encoding stage 28b which is an entropy coder entropy coding quantized prediction residual signal 34 into datastream 12.
• Encoder 14 further comprises the prediction residual signal reconstruction stage 36 connected to the output of quantizer 30 so as to reconstruct from the transformed and quantized prediction residual signal 34 the prediction residual signal in a manner also available at the decoder, i.e. taking the coding loss is quantizer 30 into account.
• the prediction residual reconstruction stage 36 comprises a dequantizer 38 which perform the inverse of the quantization of quantizer 30, followed by an inverse transformer 40 which performs the inverse transformation relative to the transformation performed by transformer 32 such as the inverse of the spectral decomposition such as the inverse to any of the above-mentioned specific transformation examples.
• Encoder 14 comprises an adder 42 which adds the reconstructed prediction residual signal as output by inverse transformer 40 and the prediction signal 24 so as to output a reconstructed signal, i.e. reconstructed samples. This output is fed into a predictor 44 of encoder 14 which then determines the prediction signal 24 based thereon. It is predictor 44 which supports all the prediction modes already discussed above with respect to Fig. 1.
• Fig. 2 also illustrates that in case of encoder 14 being a video encoder, encoder 14 may also comprise an in-loop filter 46 with filters completely reconstructed pictures which, after having been filtered, form reference pictures for predictor 44 with respect to inter-predicted block.
• encoder 14 operates block-based.
• the block bases of interest is the one subdividing picture 10 into blocks for which the intra-prediction mode is selected out of a set or plurality of intra-prediction modes supported by predictor 44 or encoder 14, respectively, and the selected intra-prediction mode performed individually.
• Other sorts of blocks into which picture 10 is subdivided may, however, exist as well.
• the above-mentioned decision whether picture 10 is inter-coded or intra-coded may be done at a granularity or in units of blocks deviating from blocks 18.
• the inter/intra mode decision may be performed at a level of coding blocks into which picture 10 is subdivided, and each coding block is subdivided into prediction blocks.
• Prediction blocks with encoding blocks for which it has been decided that intra-prediction is used are each subdivided to an intra-prediction mode decision. To this, for each of these prediction blocks, it is decided as to which supported intra-prediction mode should be used for the respective prediction block.
• These prediction blocks will form blocks 18 which are of interest here.
• Prediction blocks within coding blocks associated with inter-prediction would be treated differently by predictor 44. They would be inter-predicted from reference pictures by determining a motion vector and copying the prediction signal for this block from a location in the reference picture pointed to by the motion vector.
• Another block subdivisioning pertains the subdivisioning into transform blocks at units of which the transformations by transformer 32 and inverse transformer 40 are performed.
• Transformed blocks may, for instance, be the result of further subdivisioning coding blocks.
• the examples set out herein should not be treated as being limiting and other examples exist as well.
• the subdivisioning into coding blocks may, for instance, use multi-tree subdivisioning, and prediction blocks and/or transform blocks may be obtained by further subdividing coding blocks using multi-tree subdivisioning, as well.
• a decoder or apparatus for block-wise decoding fitting to the encoder 14 of Fig. 1 is depicted in Fig. 3 .
• This decoder 54 does the opposite of encoder 14, i.e. it decodes from datastream 12 picture 10 in a block-wise manner and supports, to this end, a plurality of intra-prediction modes.
• the decoder 54 may comprise a residual provider 156, for example. All the other possibilities discussed above with respect to Fig. 1 are valid for the decoder 54, too.
• decoder 54 may be a still picture decoder or a video decoder and all the prediction modes and prediction possibilities are supported by decoder 54 as well.
• encoder 14 chooses or selects coding decisions according to some optimization such as, for instance, in order to minimize some cost function which may depend on coding rate and/or coding distortion.
• One of these coding options or coding parameters may involve a selection of the intra-prediction mode to be used for a current block 18 among available or supported intra-prediction modes.
• the selected intra-prediction mode may then be signaled by encoder 14 for current block 18 within datastream 12 with decoder 54 redoing the selection using this signalization in datastream 12 for block 18.
• decoder 54 may be a predictive decoder operating on a block-bases and besides intra-prediction modes, decoder 54 may support other prediction modes such as inter-prediction modes in case of, for instance, decoder 54 being a video decoder. In decoding, decoder 54 may also use the coding order 20 discussed with respect to Fig.
• the description of the mode of operation of encoder 14 shall also apply to decoder 54 as far the subdivision of picture 10 into blocks is concerned, for instance, as far as prediction is concerned and as far as the coding of the prediction residual is concerned. Differences lie in the fact that encoder 14 chooses, by optimization, some coding options or coding parameters and signals within, or inserts into, datastream 12 the coding parameters which are then derived from the datastream 12 by decoder 54 so as to redo the prediction, subdivision and so forth.
• Fig. 4 shows a possible implementation of the decoder 54 of Fig. 3 , namely one fitting to the implementation of encoder 14 of Fig. 1 as shown in Fig. 2 .
• the same reference signs, provided with an apostrophe are used in Fig. 4 in order to indicate these elements.
• adder 42', optional in-loop filter 46' and predictor 44' are connected into a prediction loop in the same manner that they are in encoder of Fig. 2 .
• dequantized and retransformed prediction residual signal applied to added 42' is derived by a sequence of entropy decoder 56 which inverses the entropy encoding of entropy encoder 28b, followed by the residual signal reconstruction stage 36' which is composed of dequantizer 38' and inverse transformer 40' just as it is the case on encoding side.
• the decoder's output is the reconstruction of picture 10.
• the reconstruction of picture 10 may be available directly at the output of adder 42' or, alternatively, at the output of in-loop filter 46'.
• Some post-filter may be arranged at the decoder's output in order to subject the reconstruction of picture 10 to some post-filtering in order to improve the picture quality, but this option is not depicted in Fig. 4 .
• block 18 may have any shape. It may be, for instance, of rectangular or quadratic shape. Moreover, although the above description of the mode of operation of encoder 14 and decoder 54 often mentioned a "current block" 18 it is clear that encoder 14 and decoder 54 act accordingly for each block for which an intra-prediction mode is to be selected. As described above, there may be other blocks as well, but the following description focuses on those blocks 18 into which picture 10 is subdivided, for which an intra-prediction mode is to be selected.
• Fig. 5 shows a current block 18, i.e. a block currently to be encoded or decoded.
• Fig. 5 shows a set 60 of neighboring samples 62, i.e. samples 62 with spatially neighbor block 18.
• the samples 64 within block 18 are to be predicted.
• the prediction signal to be derived is, thus, a prediction for each sample 64 within block 18.
• a plurality 66 of prediction modes are available for each block 18 and if block 18 is to be intra-predicted, this plurality 66 of modes merely comprises inter-prediction modes.
• a selection 68 is performed at encoder and decoder side in order to determine one of the intra-prediction modes out of the plurality 66 to be used to predict (71) the prediction signal for block 18 on the basis of the neighboring sample set 60.
• the examples described further below differ with respect to the available intra-prediction modes 66 and the mode of operation with respect to selection 68 such as, for instance, whether side information is set in the datastream 12 with respect to selection 68 with respect to block 18 or not. The description of these examples, however, starts with a concrete description providing mathematical details.
• the selection for a certain block 18 to be intra-predicted is associated with corresponding side information signalization 70 and the datastream and the plurality 66 of intra-prediction modes comprises a set 72 of neural network-based intra-prediction modes as well as a set 74 of further intra-prediction mode of heuristic design.
• One of the intra-prediction modes of set 74 may, for instance, be a DC prediction mode according to which some mean value is determined on the basis of the neighboring sample set 60 and this mean value is assigned to all samples 64 within block 18.
• set 74 may comprise inter-prediction modes which may be called angular inter-prediction modes according to which sample values of the neighboring sample set 60 are copied into block 18 along a certain intra-prediction direction with this intra-prediction direction differing among such angular intra-prediction modes.
• Fig. 5 shows that the datastream 12 comprises, in addition to the optionally present side information 70 concerning the selection 68 out of the plurality 66 of intra-prediction modes, a portion 76 into which the prediction residual encoded which coding may, as discussed above, optionally involve transform coding with quantization in transform domain.
• Fig. 6 shows the general mode of operation for an intra-prediction block at encoder and decoder.
• Fig. 6 shows block 18 along with the neighboring samples set 60 on the basis of which the intra-prediction is performed.
• this set 60 may vary among the intra-prediction modes of the plurality 66 of intra-prediction modes in terms of cardinality, i.e. the number of samples of set 60 actually used according to the respective intra-prediction mode for determining the prediction signal for block 18. This is, however, for ease of understanding, not depicted in Fig. 6.
• FIG. 6 shows that encoder and decoder have one neural network 80 0 to 80 KB -1 for each of the neural network-based intra-prediction modes of set 72.
• Set 60 is applied to the respective neural network so as to derive the corresponding intra-prediction mode among set 72.
• Fig. 6 rather representatively shows one block 82 as providing on the basis of the input, namely the set 60 of neighboring samples, the one or more prediction signals of the one or more intra-prediction modes of set 74, e.g. the DC mode prediction signal and/or angular intra-prediction mode prediction signal.
• the specific example set out hereinafter also provides encoder and decoder with another neural network 84 which is dedicated to provide a probability value for each neural network-based intra-prediction mode within set 72 on the basis of a set 86 of neighboring samples which may or may not coincide with set 60.
• the probability values thus provided when the neural network 84 assists in rendering the side information 70 for the mode selection more effective.
• the probability values provided by the neural network 84 enable to use the variable length code within the side information 70 as an index into an ordered list of intra-prediction modes ordered according to the probability values output by neural network 84 for the neural network-based intra-prediction modes within set 72, thereby optimizing or reducing the code rate for the side information 70.
• the mode selection 68 is effectively performed depending on both, the probability values provided by the further neural network 84 as well as the side information 70 within datastream 12.
• B ⁇ Z 2 be a block of a video frame, i.e. block 18.
• B has M pixels.
• R M the content of a video signal on B.
• B rec ⁇ Z 2 of B that has L pixels and on which an already reconstructed image rec ⁇ R L is available, i.e. sample sets 60 and 86 although they may alternatively differ.
• F ( rec ) a predictor for im.
• section 1.1 we shall describe how to deal with the first item.
• section1.2 it is described how to handle items 2 to 3.
• section1.4 it is described how to take item 4 into account.
• section1.5 it is described how to deal with the last item.
• a data driven approach to determine unknown parameters that are used in a video codec is usually set up as an optimization algorithm that tries to minimize a predefined loss function on a given set of training examples.
• the latter loss function should satisfy some smoothness requirements.
• a video encoder like HEVC performs best when it makes its decisions my minimizing the Rate-Distortion costs D + ⁇ ⁇ R.
• D is the reconstruction error of the decoded video signal
• R is the rate, i.e. the number of bits needed to code the video signal.
• ⁇ ⁇ R is a Lagrangian Parameter that depends on the chosen Quantization Parameter.
• the true function D + ⁇ ⁇ R is typically very complex and is not given by a closed expression one can feed a data driven optimization algorithm with. Thus, we approximate either the whole function D + ⁇ ⁇ R or at least the rate function R by a piecewise smooth function.
• the functions in (2) define the neural network 80 0 - 80 KB -1 in Fig. 6 .
• This function defines a VLC code length distribution used for side information 70. i.e. the code lengths assocaited by side information 70 with cad ponite more of set 72.
• R ⁇ is the function defined in section 2.1, for given ⁇ 1 B , ... , ⁇ K B B , ⁇ B ⁇ R T , reconstructed image rec ⁇ R L and original image im ⁇ R M , we let k opt B im , rec , ⁇ 1 B , ... , ⁇ K B B , ⁇ B ⁇ 1 , ... , K B denote the smallest k ⁇ ⁇ 1, ..., K B ⁇ with the property that R ⁇ im ⁇ F ⁇ B , k B rec + M ⁇ B B rec k ⁇ R ⁇ im ⁇ F ⁇ B , l B rec + M ⁇ B B rec l for all l ⁇ ⁇ 1, ..., K B ⁇ .
• each of these functions consists of a sequence of compositions of functions which are either: 1) An affine transofrmation Aff or 2) A non-linear activation function Act.
• affine transformation Aff R m ⁇ R n
• Aff x L x + b
• Each linear map L : R m ⁇ R n is completely determined by a matrix in R n ⁇ m , i.e. corresponds uniquely to a vector ⁇ L ⁇ R m ⁇ n .
• Each affine function Aff : R m ⁇ R n is thus completely determined by m ⁇ n + n weights, i.e. by a vector ⁇ ⁇ R m ⁇ n + n .
• Aff ⁇ for each ⁇ ⁇ R m ⁇ n + n we shall write Aff ⁇ for the unique affine transformation that corresponds to ⁇ in the aforementioned way.
• ⁇ : R ⁇ R may alternatively be a piecewise smooth function, for example.
• T ⁇ N , L ⁇ N and M ⁇ N are as in (1).
• F ⁇ B Aff ⁇ k ⁇ ⁇ ⁇ Aff ⁇ k ⁇ 1 ⁇ ⁇ ⁇ Aff ⁇ k ⁇ 2 ⁇ ... ⁇ ⁇ ⁇ Aff ⁇ 1 .
• F ⁇ B would, thus, describe a neural network 80 i parametrized using paramters ⁇ .
• Each row of Aff ⁇ j incorpartes the weights controlling as to how strong a signal strength respectively activation of each of the m predecessor neurons is forwarded to the respective neuron of the neuron layer j which corresponds to the respective row.
• ⁇ controlls for each neuron of neuron layer j the non-linear mapping of its linear combination of forwarded predecessor neuron activations onto its own activation.
• the number of neurons per layer may vary.
• the number of nuron layers k may vary among the various neural networks 80 j , i.e. for different j. Note, that the non-linear function might vary per neurion layer or even per neuron or at some other units.
• T ⁇ N , L ⁇ N and K B ⁇ N are as in (3).
• G ⁇ B : Aff ⁇ k ′ ⁇ ⁇ ⁇ Aff ⁇ k ′ ⁇ 1 ⁇ ⁇ ⁇ Aff ⁇ k ′ ⁇ 2 ⁇ ... ⁇ ⁇ ⁇ Aff ⁇ 1 .
• G ⁇ B would, thus, describe a neural network 84 parametrized using paramters ⁇ . It would be a sequence of linear functions Aff ⁇ j and non-linear functions ⁇ , just as it has been described above with respect to the neuron layers concerning the prediction signal computation.
• the number of neuron layers k ' of neural network 84 may differ from one or more of the number of neuron layers k of neural networks 80 i .
• F fix B F 1 , fix B , ... , F K ⁇ B
• fix B be a set of fixed intra prediction functions that are already available.
• F fix B can consist of the DC- or Planar-prediction of HEVC and angular predictions defined according to HEVC; all those predictions may also include a preliminary smoothing of the reconstructed samples.
• L fix R M ⁇ R L ⁇ 1 , ... , K ⁇ B ⁇ R
• B' ⁇ B we define ⁇ B
• Loss F fix B total as follows.
• BL min ⁇ BL be the set of all minimal elements in .
• the integration of intra prediction functions whose design is based on a data driven learning approach into an existing hybrid video codec.
• the description had two main parts. In the first part, we described a concrete algorithm for an offline training of intra prediction functions. In the second part, we described how a video decoder may use the latter prediction functions in order to generate a prediction signal for a given block.
• the apparatus 54 supports a plurality of intra-prediction modes comprising, at least, a set 72 of intra-prediction modes according to which the intra-prediction signal for a current block 18 of the picture 10 is determined by applying a first set 60 of neighboring samples of the current block 18 onto a neural network 80 i .
• the apparatus 54 is configured to select (68) for the current block 18 one intra-prediction mode out of the plurality 66 of intra-prediction modes and predict (71) the current block 18 using the one intra-prediction mode, namely using the corresponding neural network 80 m having been selected.
• decoder 54 does not use, and does not comprise, the further neural network 84.
• the decoder 54 could decode from datastream 12 an index for block 18 using a variable length code, the code length of which are indicated in M B , and the decoder 54 would perform the selection 68 based on this index.
• the index would be part of the side information 70.
• the decoder 54 may alternatively derive a ranking among the set 72 of neural network-based intra-prediction modes depending on a first portion of the datastream which relates to a neighborhood of the current block 18 in order to obtain an ordered list of intra-prediction modes with selecting the intra-prediction mode finally to be used out of the ordered list of intra-prediction modes depending on a second portion of the datastream other than the first portion.
• the "first portion” may, for instance, relate to a coding parameter or prediction parameter related to one or more block neighboring current block 18.
• the "second portion” may then be an index, for instance, pointing into, or being an index of, the neural network-based intra-prediction mode set 72.
• the decoder 54 comprises the further neural network 84 which determines, for each intra-prediction mode of the set 72 of intra-prediction modes, a probability value by applying set 86 of neighboring samples thereonto and ordering these probability values in order to determine a rank for each intra-prediction mode of set 72, thereby obtaining an ordered list of intra-prediction modes.
• An index in the datastream 12 as part of side information 70 is then used as an index into the ordered list.
• this index may be coded using variable length code for which M B indicates the code length.
• decoder 54 may use the just-mentioned probability values determined by the further neural network 84 for each neural network-based intra-prediction mode of set 72 so as to efficiently perform entropy coding of the index into set 72.
• the symbol alphabet of this index which is part of the side information 70 and used as an index into set 72, would comprise a symbol or value for each of the modes within set 72, and the probability values provided by neural network 84 would, in case of neural network 84 design according to the above description, provide probability values which would lead to efficient entropy coding in that these probability values closely represent the actual symbol statistics.
• arithmetic coding could be used, for instance, or probability interval partitioning entropy (PIPE) coding.
• Each neural network 80 i once advantageously parametrized for encoder and decoder in accordance with, for example, the above description in sections 1 and 2, derives the prediction signal for the current block 18 without any additional guidance in the datastream.
• the existence of other intra-prediction modes besides the neural network-based ones in set 72 is optional. They have been indicated above by set 74.
• one possible way of selecting set 60 i.e. the set of neighboring samples forming the input for the intra-prediction 71, may be such that this set 60 is the same for the intra-prediction modes of set 74, i.e.
• set 60 for the neural network-based intra-prediction modes being larger in terms of the number of neighboring samples included in set 60 and influencing the intra-prediction 71.
• the cardinality of set 60 may be larger for neural network-based intra-prediction modes 72 compared to the other modes of set 74.
• set 60 of any intra-prediction mode of set 74 may merely comprise neighboring samples along a one-dimensional line extending alongside to sides of block 18 such as the left hand one and the upper one.
• Set 60 of the neural network-based intra-prediction modes may cover an L-shaped portion extending alongside the just-mentioned sides of block 18 but being wider than just one-sample wide as set 60 for the intra-prediction modes of set 74.
• the L shaped portion may additionally extend beyond the just mentioned sides of block 18. In this manner, neural network-based intra-prediction modes may result into a better intra-prediction with a correspondingly lower prediction residual.
• the side information 70 conveyed in the datastream 12 to an intra-predicted block 18 may comprise a fleck which generally indicates whether the selected intra-prediction mode for block 18 is member of set 72 or member of set 74.
• This fleck is, however, merely optional with side information 70 indicating, for instance, an index into a whole plurality 66 of intra-prediction modes including both sets 72 and 74.
• the just-discussed alternatives are, in the following, briefly discussed with respect to the Figs. 7a to 7d .
• the Figs. define both, decoder and encoder concurrently, namely in terms of their functionality with respect to an intra-predicted block 18.
• the differences between the encoder mode of operation and the decoder mode of operation with respect to an intra-coded block 18 is, on the one hand, the fact that the encoder performs all or at least some of the intra-prediction modes 66 available so as to determine at 90 a best one in terms of, for instance, some cost function minimizing sense, and that the encoder forms data stream 12, i.e., codes date there into, while the decoder derives the data therefrom by decoding and reading, respectively.
• a flag 70a within the side information 70 for block 18 indicates whether the intra-prediction mode determined to be the best mode for block 18 by the encoder in step 90, is within set 72, i.e., is neural network based intra-prediction mode, or within set 74, i.e., one of the non-neural network based intra-prediction modes.
• the encoder inserts flag 70a into data stream 12 accordingly, while the decoder retrieves it therefrom.
• Fig. 7a assumes that the determined intra-prediction mode 92 is within set 72.
• the separate neural network 84 determines a probability value for each neural network based intra-prediction mode of set 72 and using these probability values set 72 or, to be more precise, the neural network based intra-prediction modes therein are ordered according to their probability values such as in descending order of their probability values, thereby resulting into an ordered list 94 of intra-prediction modes.
• An index 70b being part of the side information 70 is then coded by the encoder into data stream 12 and decoded therefrom by the decoder.
• the decoder accordingly, is able to determine which set of sets 72 and 74.
• the intra-prediction mode to be used for block 18 is located in, and to perform the ordering 96 of set 72 in case of the intra-prediction mode to be used being located in set 72. It might be that an index is also transmitted in data stream 12 in case of the determined intra-prediction mode being located in set 74.
• the decoder is able to generate the prediction signal for block 18 using the determined intra-prediction mode by controlling the selection 68 accordingly
• Fig. 7b shows an alternative according to which the flag 70a is not present in data stream 12.
• the ordered list 94 would not only comprise the intra-prediction modes of set 72, but also intra-prediction modes of set 74.
• the index within side information 70 would be an index into this greater ordered list and indicate the determined intra-prediction mode, i.e., the one determined be optimization 90.
• the ranking between intra-prediction modes of set 72 relative to the intra-prediction modes of set 74 may be determined by other means such as inevitably arranging the neural network based intra-prediction modes of set 72 to precede the modes of set 74 in the order list 94 or to arrange them alternatingly relative to each other. That is, the decoder is able to derive the index from data stream 12, use the index 70 as in index into the order list 94 with deriving the order list 94 from the plurality of intra-prediction modes 66 using the probability values output by neural network 84.
• Fig. 7c shows a further variant. Fig.
• FIG. 7c show a case of not using flag 70a, but the flag could be used alternatively.
• the issue which Fig. 7c is directed pertains to the possibility that neither encoder nor decoder uses neural network 84. Rather, the ordering 96 is derived by other means such as coding parameters conveyed within data stream 12 with respect to one or more neighboring blocks 18, i.e., portions 98 of a data stream 12 which pertains to such one or more neighboring blocks.
• Fig. 7d shows a further variant of Fig. 7a , namely the one according to which the index 70b is coded using entropy coding and decoded from data stream 12 using entropy decoding, commonly denoted using reference sign 100.
• the sample statistics or the probability distribution used for the entropy coding 100 is controlled by the probability values output by neural network 84 as explained above, this renders the entropy coding of index 70b very efficient.
• set 74 modes may not be present. Accordingly, the respective module 82 may be missing and flag 70a would be unnecessary anyway.
• Fig. 8 shows an apparatus for designing the set of intra-prediction modes of set 72 to be used for the block-based picture coding.
• the apparatus 108 comprises a parameterizable network 109 which inherits or comprises parameterizable versions of neural networks 80 0 to 80 KB -1 as well as neural network 84.
• Fig. 8 depicted as individual units, i.e., neural network 84 0 for providing the probability value for neural network based intra-prediction mode 0 to neural network 84 KB-1 for providing the probability value associated with the neural network based intra-prediction mode K B-1 .
• the parameters 111 for parametrizing neural networks 84 and the parameters 113 for parametrizing neural networks 80 0 to 80 KB-1 are input or applied to respective parameter inputs of these neural networks by an updater 110.
• Apparatus 108 has access to a reservoir or a plurality of picture test blocks 114 along with corresponding neighboring samples sets 116. Pairs of these blocks 114 and their associated neighboring sample sets 116 are sequentially used by apparatus 108.
• a current picture test block 114 is applied to parameterizable neural network 109 so that neural networks 80 provide a prediction signal 118 for each neural network based intra-prediction mode of set 72, and each neural network 80 provides a probability value for each of these modes.
• these neural networks use their current parameters 111 and 113.
• the cost estimate is in any case a sum of two add-ins, one of which is an estimate of the coding cost for the prediction residual indicated as the term with R ⁇ in the above inequality, and another add-in estimating the coding costs for indicating the mode.
• the cost estimators 122 also obtain the original content of the current picture test block 114.
• the neural networks 80 and 84 had at their inputs applied thereto the corresponding neighboring sample sets 116.
• the cost estimate 124 as output by cost estimators 122 is received by a minimum cost selector 126 which determines the mode minimizing or having minimum cost estimate associated therewith. In the above mathematical notation, this has been k opt B .
• the updater receives this optimum mode and uses a coding cost function having a first add in forming residual rate estimate depending on the prediction signal 118 obtained for the intra-prediction mode of lowest coding estimate, and a second add-in forming a mode signaling side information rate estimate depending on the prediction signal and the probability value obtained for the intra-prediction mode of lowest coding cost estimate as indicated by selector 126. As indicated above, this may be done using a gradient distant.
• the coding cost function is, thus, differentiable and in the above mathematical representation an example of this function was given in equation 5.
• the second add-in relating to the mode signaling side information rate estimate computed the cross entropy for the intra-prediction mode of lowest coding cost estimate.
• the updater 110 seeks to update parameters 111 and 113 so as to reduce the coding cost function and then these updated parameters 111 and 113 are used by the parametrizable neural network 109 so as to process the next picture test block of the plurality 112.
• the updater 110 may be a mechanism controlling that primarily those pairs of picture test blocks 114 and their associated neighboring sample sets 116 are applied for the recursive update process for which the intra-prediction is, in rate distortion sense, preferably done without any block sub-division, thereby avoiding that the parameters 111 and 113 are optimized too much on the basis of picture test blocks for which, anyway, a coding in units of sub-blocks thereof is more cost effective.
• Fig. 9a seeks to outline the mode of operation of an encoder and a decoder in accordance with an example wherein the description thereof is provided in a manner focusing on the differences to the description brought forward above with respect to Fig. 7a .
• the plurality 66 of supported intra-prediction modes may or may not comprise neural network-based intra-prediction modes and may or may not comprise non-neural network-based intra-prediction modes.
• the neural network 84 computes, on the basis of the neighboring sample set 86, probability values for the supported intra-prediction modes 66 so that the plurality 66 of intra-prediction modes may be turned into the ordered list 94.
• the index 70 within datastream 12 for block 18 points into this ordered list 94.
• the neural network 84 thus, assists in lowering the side information rate to be spent for the intra-prediction mode signalization.
• Fig. 9b shows an alternative to Fig. 9a in that instead of the ordering, entropy de/encoding 100 of the index 70 is used with controlling the probability or simple statistics thereof, i.e. controlling the entropy probability distribution for entropy de/encoding in en/decoder, according to the probability values determined for the neural network 84 for each mode of plurality 66.
• Fig. 10 shows an apparatus for designing or parametrizing neural network 84. It is, thus, an apparatus 108 for designing a neural network for assisting in selecting among a set 66 of intra-prediction modes.
• an apparatus 108 for designing a neural network for assisting in selecting among a set 66 of intra-prediction modes.
• the parametrizable neural network 109 of apparatus 108 is merely parametrizable with respect these blocks.
• the prediction signal computer 170 which needs, however, not to be parametrizable according to Fig. 10 .
• the 10 computes costs estimates for each mode on the basis of the prediction signal 118 as computed by the corresponding prediction signal computer 170 and, optionally, on the basis of the corresponding probability value as determined by the corresponding neural network block for this mode.
• the minimum cost selector 126 selects the mode of the minimum cost estimate and the updater 110 updates the parameters 111 for the neural 84.
• FIG. 7a to 7d The following is noted with respect to the description of Figs. 7a to 7d and 9a and 9b .
• a common feature of the examples of Figs. 9a and 9b which is also used by some of the examples of Figs. 7a to 7d was the fact that the probability values of the neural network values in order to improve or reduce the overhead associated with the side information 70 for signaling the mode determined on the encoder side at the optimization process 90 to the decoder.
• the examples of Figs. 9a and 9b may be varied to the extent that no side information 70 is spent in datastream 12 with respect to the mode selection at all.
• the probability values output by neural network 84 for each mode may be used to synchronize the mode selection between encoder and decoder inevitably. In that case, there would be no optimization decision 90 at the encoder side with respect to the mode selection. Rather, the mode to be used among set 66 would be determined on encoder and decoder side in the same manner.
• a similar statement is true with respect to corresponding examples of Figs. 7a to 7d when varied so as to not use any side information 70 in datastream 12. Back to the examples of Figs.
• the dependency on the probability values may not only affect the coding of the side information 70 into datastream 12 using, for instance, a respective variable length coding of an index into the ordered list or using entropy en/decoding with a probability distribution estimation depending on the neural network's probability values, but also the optimization step 90: here, the code rate for transmitting side information 70 may be taken into account and may, thus, influence the determination 90.
• Fig. 11-1 shows a possible implementation of an encoder 14-1, namely one where the encoder is configured to use transform coding for encoding the prediction residual although this is nearly an example and the present application is not restricted to that sort of prediction residual coding.
• encoder 14-1 comprises a spatial-domain subtractor 22 configured to subtract from the inbound signal, i.e. picture 10 or, on a block basis, current block 18, the corresponding prediction signal 24-1 so as to obtain the spatial-domain prediction residual signal 26 which is then encoded by a prediction residual encoder 28 into a datastream 12.
• the prediction residual encoder 28 comprises a lossy encoding stage 28a and a lossless encoding stage 28b.
• the lossy encoding stage 28a receives the prediction residual signal 26 and comprises a quantizer 30 which quantizes the samples of the prediction residual signal 26.
• the present example uses transform coding of the prediction residual signal 26 and accordingly, the lossy encoding stage 28a comprises a transform stage 32 connected between subtractor 22 and quantizer 30 so as to transform such a spectrally decomposed prediction residual 27 with a quantization of quantizer 30 taking place on the transformed coefficients where presenting the residual signal 26.
• the transform may be a DCT, DST, FFT, Hadamard transform or the like.
• the transformed and transform-domain quantized prediction residual signal 34 is then subject to lossless coding by the lossless encoding stage 28b which is an entropy coder entropy coding quantized prediction residual signal 34 into datastream 12.
• Encoder 14-1 further comprises a transform-domain prediction residual signal reconstruction stage 36-1 connected to the transform-domain output of quantizer 30 so as to reconstruct from the transformed and quantized prediction residual signal 34 (in the transform domain) the prediction residual signal in a manner also available at the decoder, i.e. taking the coding loss of quantizer 30 into account.
• the prediction residual reconstruction stage 36-1 comprises a dequantizer 38-1 which performs the inverse of the quantization of quantizer 30 to obtain a dequantized version 39-1 of the prediction residual signal 34, followed by an inverse transformer 40-1 which performs the inverse transformation relative to the transformation performed by transformer 32 such as the inverse of the spectral decomposition such as the inverse to any of the above-mentioned specific transformation examples.
• a spatial-domain output 60 which may comprise a template which will help to obtain the prediction signal 24-1.
• the predictor 44-1 may provide a transform-domain output 45-1 which, once inverse-transformed at the inverse transformer 51-1, will provide the prediction signal 24-1 in the spatial domain (the prediction signal 24-1 will be subtracted from the inbound signal 10, to obtain the prediction residual 26 in the time domain).
• an in-loop filter 46-1 filters completely reconstructed pictures 60 which, after having been filtered, form reference pictures 47-1 for predictor 44-1 with respect to inter-predicted block (accordingly, in these cases an adder 57-1 input from the elements 44-1 and 36-1 is necessary, but there is no necessity for the inverse transformer 51-1, as indicated by the dotted line 53-1, for providing the prediction signal 24-1 to the subtractor 22).
• encoder 14-1 (at the prediction residual reconstruction stage 36-1) comprises a transform-domain adder 42-1, which is positioned between the dequantizer 38-1 and the inverse transformer 40-1.
• the transform-domain adder 42-1 provides the inverse transformer 40-1 with a sum 43-1 (in the transform domain) of the dequantized version 39-1 of the prediction residual signal 34 (as provided by the dequantizer 38-1) with a transform-domain prediction signal 45-1 as provided by a transform-predictor 44-1.
• the predictor 44-1 may obtain, as a feedback input, the output from the inverse transformer 40-1.
• the prediction signal 24-1 in the spatial domain is obtained from a prediction signal 45-1 in the transform domain.
• the transform-domain predictor 44-1 which may operate with neural networks according to the examples above, is input by signals in the spatial domain but outputs signals in the transform domain.
• Fig. 11-2 shows a possible implementation of a decoder 54-2, namely one fitting to the implementation of encoder 14-1.
• the same reference signs, provided with a "-2" are used in Fig. 11-2 in order to indicate these elements.
• adder 42-2, optional in-loop filter 46-2 and predictor 44-2 are connected into a prediction loop in the same manner that they are in encoder of Fig. 11-1 .
• dequantized and retransformed prediction residual signal 24-2 (e.g., 60), is derived by a sequence of entropy decoder 56 which inverses the entropy encoding of entropy encoder 28b, followed by the residual signal reconstruction stage 36-2 which is composed of dequantizer 38-2 and inverse transformer 40-2 just as it is the case on encoding side.
• the decoder's output is the reconstruction of picture 10.
• Some post-filter 46-2 may be arranged at the decoder's output in order to subject the reconstruction of picture 10 to some post-filtering in order to improve the picture quality.
• the reconstructed signal 24-2 is provided to a predictor 44-2, which may operate with neural networks according to the examples of Figs. 5-10 .
• the predictor 44-2 may provide a transform-domain prediction value 45-2.
• the dequantizer 38-2 provides a dequantized version 39-2 of the prediction residual signal 34 (in the transform domain) which is not directly provided to the inverse transformer 40-2. Instead, the dequantized version 39-2 of the prediction residual signal 34 is input to an adder 42-2, so as to be composed with the transform-domain prediction value 45-2. Accordingly, there is obtained a transform-domain reconstructed signal 43-2, which, when subsequently inversely transformed by the inverse transformer 40-2, becomes the reconstructed signal 24-2 in the spatial domain, to be used for displaying the image 10.
• Fig. 12 Both, decoder and encoder concurrently, namely in terms of their functionality with respect to an intra-predicted block 18.
• the differences between the encoder mode of operation and the decoder mode of operation with respect to an intra-coded block 18 is, on the one hand, the fact that the encoder performs all or at least some of the intra-prediction modes 66 available so as to determine at 90 a best one in terms of, for instance, some cost function minimizing sense, and that the encoder forms data stream 12, i.e., codes date there into, while the decoder derives the data therefrom by decoding and reading, respectively.
• a flag 70a within the side information 70 for block 18 indicates whether the intra-prediction mode determined to be the best mode for block 18 by the encoder in step 90, is within set 72, i.e., is neural network based intra-prediction mode, or within set 74, i.e., one of the non-neural network based intra-prediction modes.
• the encoder inserts flag 70a into data stream 12 accordingly, while the decoder retrieves it therefrom.
• Fig. 12 assumes that the determined intra-prediction mode 92 is within set 72.
• the separate neural network 84 determines a probability value for each neural network based intra-prediction mode of set 72 and using these probability values set 72 or, to be more precise, the neural network based intra-prediction modes therein are ordered according to their probability values such as in descending order of their probability values, thereby resulting into an ordered list 94 of intra-prediction modes.
• An index 70b being part of the side information 70, is then coded by the encoder into data stream 12 and decoded therefrom by the decoder.
• the decoder accordingly, is able to determine which set of sets 72 and 74.
• the intra-prediction mode to be used for block 18 is located in, and to perform the ordering 96 of set 72 in case of the intra-prediction mode to be used being located in set 72. It might be that an index is also transmitted in data stream 12 in case of the determined intra-prediction mode being located in set 74.
• the decoder is able to generate the prediction signal for block 18 using the determined intra-prediction mode by controlling the selection 68
• the prediction residual signal 34 (in the transform domain) is encoded in the datastream 12.
• the dequantizer 38-1, 38-2 derives a transform-domain dequantized prediction residual signal 39-1, 39-2.
• the transform-domain prediction signal 45-1, 45-2 is obtained.
• the adder 42-1 sums the values 39-1 and 45-1 (or the adder 42-2 sums the values 39-2 and 45-2) with each other, to obtain the transform-domain reconstructed signal 43-1 (or 43-2).
• a spatial-domain prediction signal 24-1, 24-2 e.g., template 60
• may be used to reconstruct the block 18 (which may be, for example, displayed).
• Figs 7b-7d may be used to embody the examples of Figs. 11-1 , 11-2 , and 12 .
• a method to generate an intra prediction signal via a Neural Network is defined and it is described how this method is to be included into a video- or still-image codec.
• the predictors 44-1, 44-2 may predict into the transform domain for a predefined image transform that might be already available at the underlying codec, e.g. the Discrete Cosine Transform.
• each of the intra prediction modes that is defined for images on blocks of a specific shape induces intra prediction modes for images on larger blocks.
• B be a block of pixels with M rows and N columns on which an image im is present.
• B rec template 60 or 86
• B block 18
• new intra prediction modes defined by a Neural Network are introduced. Each of these intra prediction modes generates, using the reconstructed samples rec (24-1, 24-2), a prediction signal pred (45-1, 45-2), which is again an image on B rec .
• T be an image transform (e.g., prediction residual signal 34 as output by element 30) that is defined on images on B rec and let S be the inverse transform of T (e.g., at 43-1 or 43-2). Then the prediction signal pred (45-1, 45-2) is to be regarded as a prediction for T (im). This means that at the reconstruction stage, after the computation of pred (45-1,45-2) the image S (pred) (24-1, 24-2) has to be computed to obtain the actual prediction for the image im (10).
• pred e.g., prediction residual signal 34 as output by element 30
• the transform T we work with has some energy compaction properties on natural images. This is exploited in the following way. For each of our intra modes defined by a Neural Network, by a predefined rule the value of pred (45-1, 45-2) at specific positions in the transform domain is set to zero, independent of the input rec (24-1, 24-2). This reduces the computational complexity to obtain the prediction signal pred (45-1, 45-2) in the transform domain.
• a prediction residual res (34) is to be inverse transformed by the inverse transform S (at 40) to obtain S(res) and that S(res) is to be added to an underlying prediction signal (24) to obtain the final reconstruction signal (24).
• Figs. 11 and 12 refer to the following procedure: in the case that the prediction signal pred (45-1, 45-2) is generated by the Neural Network intra prediction method as above, the final reconstruction signal (24-1, 24-2) is obtained by the inverse transform (at 40-1, 40-2) of pred+res (where pred is 45-1 or 45-2; and res is 39-1 or 39-2, and their sum is 43-1 or 43-2, which is the transform-domain version of the final reconstruction signal 24-1, 24-2).
• a strategy is shown which may be applied, for example, to spatial-domain-based methods (e.g., Figs. 11a and 11b) and/or to transform-domain-based methods (e.g., Figs. 1-4 ).
• a neural network adapted for blocks of a particular size e.g., MxN, where M is the number of rows and N is the number of columns
• the real block 18 of the image to be reconstructed has a different size (e.g., M 1 xN 1 ). It has been noted that it is possible to perform operations which permit to make use of the neural network adapted for a particular size (e.g., MxN), without necessity of using neural networks trained ad hoc.
• the apparatus 14 or 54 may permit block-wise decoding a picture (e.g., 10) from a data stream (e.g., 12).
• the apparatus 14, 54 natively supports at least one intra-prediction mode, according to which the intra-prediction signal for a block (e.g., 136, 172) of a predetermined size (e.g., MxN) of the picture is determined by applying a first template (e.g., 130, 170) of samples which neighbors the current block (e.g., 136, 176) onto a neural network (e.g., 80).
• the apparatus may be configured, for a current block (e.g., 18) differing from the predetermined size (e.g., M 1 xN 1 ), to:
• Fig. 13a shows an example in the spatial domain.
• a spatial-domain block 18 (also indicated also as B 1 ) may be an M 1 xN 1 block for which an image im 1 is to be reconstructed (even if, at the moment, the image im 1 is not available yet).
• a template B 1,rec e.g., a set 60
• rec 1 is neighbouring to im 1 (and B 1,rec is neighboring to B 1 ).
• the block 18 and the template 60 (“second template”) may form the element 132.
• a transformation operation (here indicated as D or 134) may, for example, be applied to the element 130. It has been noted, however, that it is simply possible to apply the transformation D (130) to B 1,rec alone, by virtue of B 1 being still unknown.
• the transformation 130 may provide an element 136, which is formed of a transformed (resampled) template 130 and a block 138.
• the M 1 xN 1 block B 1 (18) (with unknown coefficients) may be theoretically transformed into an MxN block B (138) (with still unknown coefficients).
• the coefficients of block B (138) are unknown, however, there is no practical necessity for actually performing the transformation.
• the transformation D (134) transforms the template B 1,rec (60) into a different template B rec (130) with different dimensions.
• the transformation operation D (134) may be, where M 1 >M and N 1 >N (and in particular where M is a multiple of M 1 and N is a multiple of N 1 ), a downsampling operation.
• the transformation operation D may simply be based on hiding some bins in a chess-like fashion (e.g., by deleting diagonals from B 1,rec 60, to obtain the values of B rec 130).
• apparatus 14, 54 may now use (e.g., at the predictor 44, 44') the necessary neural network (e.g., by operating as in Figs. 5-10 ) natively trained for an MxN block.
• the image im 1 is obtained for block B.
• passage 138a does not use neural network, but other techniques known in the art).
• the image im 1 in block B (138) has size MxN, while the image to be displayed is requested to have size M 1 xN 1 . It has been noted, however, that it is simply possible to perform a transformation (e.g., U) 140 which transports the image im 1 in block B (138) into M 1 xN 1 .
• a transformation e.g., U
• U at 140 may be an upsampling operation. Therefore, U (140) may be obtained by introducing coefficients in the M 1 xN 1 block, besides the coefficients in the MxN block 138 as obtained at operation 138a with neural network.
• an interpolation e.g., bilinear interpolation
• guess the coefficients of im 1 that had been discarded by the transformation D.
• An M 1 xN 1 image im 1 is therefore obtained as element 142, and may be used for displaying the block image as part of the image 10.
• the M 1 xN 1 image im 1 may therefore be understood as the prediction signal 24 ( Fig. 2 ) or 24' ( Fig. 4 ) to be summed with the prediction residual signal output by the inverse transformer 40 or 40' for obtaining the reconstructed signal.
• Fig. 13b shows an example, in the transform domain (e.g., in the examples of Figs. 11-1 , 11-2 ).
• An element 162 is represented as formed by the spatial-domain template 60 (already decoded) and the spatial-domain block 18 (with unknown coefficients).
• Block 18 may have a size M 1 xN 1 and may have unknown coefficients, which are to be determined, for example, at the predictor 44-1 or 44-2.
• first template may have an L-formed shape, e.g., such as the shape of the template 130 (see above).
• the neural networks e.g., 80 0 -80 N
• the neural networks may be applied according to any of the examples above (see Figs. 5-10 ).
• the known coefficients for a version 172 of block 18 may be obtained.
• a transformation e.g., at 180 into transform domain may be operated.
• an MxN transform-domain block T (176) may be obtained.
• a technique known as zero padding may be used, e.g., by introducing values "0" in correspondence to frequency values associated to frequencies which do not exist in the MxN transform T (176).
• a zero-padding area 178 may therefore be used (it may have an L shape, for example).
• the zero-padding area 178 comprises a plurality of bins (all zero) which are inserted to the block 176 to obtain the block 182.
• This may be obtained with a transformation V from T (transformed from 172) to T 1 (182). While the dimensions of T (176) do not conform with the dimensions of the block 18, the dimensions of T 1 (182), by virtue of the insertion of the zero-padding area 178, actually conform to the dimensions of the block 18.
• the zero-padding is obtained by inserting higher-frequency bins (which have a zero value), which has a result analogous to an interpolation.
• the encoder may encode in the datastream 12 information regarding the resampling (and the use of neural networks for blocks with different size from that of the block 18), so that the decoder has the knowledge thereof.
• B 1 (e.g., 18) be a block with M 1 rows and N 1 columns and assume that M 1 ⁇ M and N 1 ⁇ N .
• B 1 rec be a neighborhood of (e.g., template 60 in adjacent to) B 1 and assume that the region B rec (e.g., 130) is regarded as a subset of B 1,rec ,.
• im 1 e.g., 138
• rec 1 e.g., the coefficients on B 1,rec
• the solutions above are based on a predefined downsampling operation D (e.g., 134, 166) which maps images on B 1 , rec to images on B 1 .
• D can be the operation of applying a smoothing filter followed by a factor two downsampling operation in each direction.
• D (rec 1 ) can be regarded as a reconstructed image on B rec .
• the prediction signal pred (e.g., 45-2) is to be regarded as a prediction signal in the transform domain with respect to an image transform T on B with inverse transform S.
• T 1 be an image transform on B 1 with inverse transform S 1 .
• a predefined mapping V is given which maps images from the transform domain of T to the transform domain of T 1 .
• T is the Discrete Cosine Transform on M ⁇ N blocks with inverse transform S
• T 1 is the Discrete Cosine Transform on M 1 ⁇ N 1 with inverse transform S 1
• a block of transform coefficients on B can be mapped to a block of transform coefficients on B 1 by zero padding and scaling (see, for example, 178).
• V (pred) to obtain an element of the transform domain for T 1 that is to be regarded as a prediction signal for T 1 (im 1 ).
• the signal V (pred) might now be further processed as described above.
• Neural Network based operation can be used to rank several intra-prediction modes on a given block B by generating a conditional probability distribution among these modes and how this ranking can be used to signal which intra prediction mode is to be applied at the current block.
• a downsampling operation e.g., 166
• a downsampling operation e.g., 166
• a ranking for the extension of the prediction modes to the larger Block B 1 just described yields a ranking for the extension of the prediction modes to the larger Block B 1 just described and can thus be used to signal which extended mode is to be used on the block B 1 .
• Neural Network based intra prediction modes from a smaller block B are to be used to generate a prediction signal can be either predefined or can be signaled as a side information in the underlying video codec.
• a decoder as above maybe and/or comprise an encoder as above or vice versa.
• the encoder 14 may be or comprise the decoder 54 (or vice versa); encoder 14-1 may be the decoder 54-2 (or vice versa), etc.
• the encoder 14 or 14-1 may also be understood as containing itself a decoder, as the quantized prediction residual signals 34 form a stream which is decoded to obtain the prediction signal 24 or 24-1.
• aspects have been described in the context of an apparatus, it is clear that these aspects also represent a description of the corresponding method, where a block or device corresponds to a method step or a feature of a method step. Analogously, aspects described in the context of a method step also represent a description of a corresponding block or item or feature of a corresponding apparatus.
• Some or all of the method steps may be executed by (or using) a hardware apparatus, like for example, a microprocessor, a programmable computer or an electronic circuit. In some examples, one or more of the most important method steps may be executed by such an apparatus.
• the inventive encoded data stream can be stored on a digital storage medium or can be transmitted on a transmission medium such as a wireless transmission medium or a wired transmission medium such as the Internet.
• examples of the invention can be implemented in hardware or in software.
• the implementation can be performed using a digital storage medium, for example a floppy disk, a DVD, a Blu-Ray, a CD, a ROM, a PROM, an EPROM, an EEPROM or a FLASH memory, having electronically readable control signals stored thereon, which cooperate (or are capable of cooperating) with a programmable computer system such that the respective method is performed. Therefore, the digital storage medium may be computer readable.
• Some examples according to the invention comprise a data carrier having electronically readable control signals, which are capable of cooperating with a programmable computer system, such that one of the methods described herein is performed.
• examples of the present invention can be implemented as a computer program product with a program code, the program code being operative for performing one of the methods when the computer program product runs on a computer.
• the program code may for example be stored on a machine readable carrier.
• an example of the inventive method is, therefore, a computer program having a program code for performing one of the methods described herein, when the computer program runs on a computer.
• a further example of the inventive methods is, therefore, a data carrier (or a digital storage medium, or a computer-readable medium) comprising, recorded thereon, the computer program for performing one of the methods described herein.
• the data carrier, the digital storage medium or the recorded medium are typically tangible and/or non-transitionary.
• a further example of the inventive method is, therefore, a data stream or a sequence of signals representing the computer program for performing one of the methods described herein.
• the data stream or the sequence of signals may for example be configured to be transferred via a data communication connection, for example via the Internet.
• a further example comprises a processing means, for example a computer, or a programmable logic device, configured to or adapted to perform one of the methods described herein.
• a processing means for example a computer, or a programmable logic device, configured to or adapted to perform one of the methods described herein.
• a further example comprises a computer having installed thereon the computer program for performing one of the methods described herein.
• a further example according to the invention comprises an apparatus or a system configured to transfer (for example, electronically or optically) a computer program for performing one of the methods described herein to a receiver.
• the receiver may, for example, be a computer, a mobile device, a memory device or the like.
• the apparatus or system may, for example, comprise a file server for transferring the computer program to the receiver.
• a programmable logic device for example a field programmable gate array
• a field programmable gate array may cooperate with a microprocessor in order to perform one of the methods described herein.
• the methods are preferably performed by any hardware apparatus.
• the apparatus described herein may be implemented using a hardware apparatus, or using a computer, or using a combination of a hardware apparatus and a computer.
• the apparatus described herein, or any components of the apparatus described herein, may be implemented at least partially in hardware and/or in software.
• the methods described herein may be performed using a hardware apparatus, or using a computer, or using a combination of a hardware apparatus and a computer.

Landscapes

• Engineering & Computer Science (AREA)
• Multimedia (AREA)
• Signal Processing (AREA)
• Compression Or Coding Systems Of Tv Signals (AREA)

Applications Claiming Priority (3)

Related Parent Applications (1)

Publications (2)

Family

ID=61868352

Family Applications (2)

Family Applications Before (1)

Country Status (7)

Families Citing this family (25)

Family Cites Families (19)

• 2019
  • 2019-03-28 EP EP19712793.9A patent/EP3777141B1/de active Active
  • 2019-03-28 KR KR1020207030912A patent/KR102524593B1/ko active Active
  • 2019-03-28 CN CN202410740877.8A patent/CN118540471A/zh active Pending
  • 2019-03-28 KR KR1020247027842A patent/KR20240133755A/ko active Pending
  • 2019-03-28 CN CN201980036297.8A patent/CN112204963B/zh active Active
  • 2019-03-28 KR KR1020237013131A patent/KR102698963B1/ko active Active
  • 2019-03-28 EP EP25198569.3A patent/EP4633164A3/de active Pending
  • 2019-03-28 JP JP2020552199A patent/JP7217288B2/ja active Active
  • 2019-03-28 WO PCT/EP2019/057882 patent/WO2019185808A1/en not_active Ceased
  • 2019-03-29 TW TW108111307A patent/TWI763987B/zh active
• 2020
  • 2020-09-25 US US17/032,113 patent/US11601672B2/en active Active
• 2023
  • 2023-01-09 US US18/094,975 patent/US12160606B2/en active Active
  • 2023-01-23 JP JP2023008219A patent/JP7516584B2/ja active Active
• 2024
  • 2024-07-03 JP JP2024107439A patent/JP7670914B2/ja active Active
  • 2024-10-23 US US18/924,688 patent/US20250056040A1/en active Pending

Also Published As

Similar Documents

Legal Events